Giter Site home page Giter Site logo

osamajbr / auto-tagging-image-search Goto Github PK

View Code? Open in Web Editor NEW
21.0 4.0 4.0 92 KB

A back-end service that tags images automatically using Google-Vision and translate tags so you can search these images by tags in two languages.

License: GNU General Public License v3.0

Python 100.00%
google-traslate-api google-vision-api elasticsearch image-recognition python

auto-tagging-image-search's Introduction

Search Images By Tagging Them

Tagging photos provides much better search capabilities, in this project I'm trying to build an intelligent way to search for images using image recognition (google-vision).

This project can be used as a back-end for backup solution, users only have to upload their images and it automatically gets tagged by google-vision services.

Also, it provides a translation capability, for example if translation for Arabic is enabled. Once the image got tags (labels) from google-vision service, all these tags will be translated using google-translation-api. So the user who is searching for 'مركبة' ( vehicle in Arabic) or the other who is looking for vehicle will get the same result.

All these processes are done in async queue, as shown in How it works section, once the recognition and the translation process are done, a document for this image will be stored in ElasticSearch in the following structure :

{
	"uploaded_at": "2017-03-25 08:54:15",
	"image_path": "/opt/personal/search-images-tags/datadir/flowers.jpg",
	"image_type": ".jpg",
	"timestamp": 1490428776,
	"en_lables": [
		"flower",
		"flora",
		"plant",
		"flower bouquet",
		"flower arranging",
		"floristry",
		"land plant",
		"petal",
		"macro photography",
		"flowering plant"
	],
	"image_fname": "flowers.jpg",
	"ar_lables": [
		"زهرة",
		"النباتية",
		"نبات",
		"باقة من الزهور",
		"ترتيب الزهور",
		"التزيين بالزهور",
		"نبات الأرض",
		"البتلة نبات",
		"تصوير الماكرو",
		"النباتات المزهرة"
	]
}

How it works

Alt text

How to run

  1. Edit the config.ini file
  2. Run the HTTP interface
$ python main.py
  1. Run the Consumer Process
$ python consumer.py
  1. Upload an image using CURL
$ curl -XPOST -F name=laptop.png -F [email protected] http://127.0.0.1:5555/upload

TO DO

  • Add search for images to the bottle application
  • Support different storage locations such (S3, Goolge Cloud Storage)
  • Imporve search for arabic words (partial search)

auto-tagging-image-search's People

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.